理论 · optimization论文趋势 2023–2026

学习理论及相关：optimization

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 1,871 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

理论 · optimization论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
20233746355123
2024304123670494
20253181961479670
20261192442147584

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

全部理论 · optimization论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 1,871 篇，第 24 / 38 页

  1. NeurIPS 2025Optimal Rates for Generalization of Gradient Descent for Deep ReLU Classification
  2. NeurIPS 2025Optimality and NP-Hardness of Transformers in Learning Markovian Dynamical Functions
  3. NeurIPS 2025Optimistic Online-to-Batch Conversions for Accelerated Convergence and Universality
  4. NeurIPS 2025Optimizing the Unknown: Black Box Bayesian Optimization with Energy-Based Model and Reinforcement Learning
  5. NeurIPS 2025Oracle-Efficient Combinatorial Semi-Bandits
  6. NeurIPS 2025Parameter-free Algorithms for the Stochastically Extended Adversarial Model
  7. NeurIPS 2025Partial Correlation Network Estimation by Semismooth Newton Methods
  8. NeurIPS 2025Pause Tokens Strictly Increase the Expressivity of Constant-Depth Transformers
  9. NeurIPS 2025PaZO: Preconditioned Accelerated Zeroth-Order Optimization for Fine-Tuning LLMs
  10. NeurIPS 2025PDPO: Parametric Density Path Optimization
  11. NeurIPS 2025Perturbation Bounds for Low-Rank Inverse Approximations under Noise
  12. NeurIPS 2025PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts
  13. NeurIPS 2025Predictability Enables Parallelization of Nonlinear State Space Models
  14. NeurIPS 2025Preference Optimization on Pareto Sets: On a Theory of Multi-Objective Optimization
  15. NeurIPS 2025Price of Parsimony: Complexity of Fourier Sparsity Testing
  16. NeurIPS 2025Probing Neural Combinatorial Optimization Models
  17. NeurIPS 2025Problem-Parameter-Free Decentralized Bilevel Optimization
  18. NeurIPS 2025Product Distribution Learning with Imperfect Advice
  19. NeurIPS 2025Provable Meta-Learning with Low-Rank Adaptations
  20. NeurIPS 2025Purest Quantum State Identification
  21. NeurIPS 2025Purity Law for Neural Routing Problem Solvers with Enhanced Generalizability
  22. NeurIPS 2025Quantum Speedups for Minimax Optimization and Beyond
  23. NeurIPS 2025Quasi-Self-Concordant Optimization with $\ell_{\infty}$ Lewis Weights
  24. NeurIPS 2025Reinforcement learning for one-shot DAG scheduling with comparability identification and dense reward
  25. NeurIPS 2025Replicable Distribution Testing
  26. NeurIPS 2025Replicable Online Learning
  27. NeurIPS 2025Rethinking Entropy in Test-Time Adaptation: The Missing Piece from Energy Duality
  28. NeurIPS 2025Rethinking Gradient Step Denoiser: Towards Truly Pseudo-Contractive Operator
  29. NeurIPS 2025Rethinking Neural Combinatorial Optimization for Vehicle Routing Problems with Different Constraint Tightness Degrees
  30. NeurIPS 2025Revisiting 1-peer exponential graph for enhancing decentralized learning efficiency
  31. NeurIPS 2025Revisiting Agnostic Boosting
  32. NeurIPS 2025Revisiting Consensus Error: A Fine-grained Analysis of Local SGD under Second-order Data Heterogeneity
  33. NeurIPS 2025Revisiting Follow-the-Perturbed-Leader with Unbounded Perturbations in Bandit Problems
  34. NeurIPS 2025Revisiting Frank-Wolfe for Structured Nonconvex Optimization
  35. NeurIPS 2025Robust Federated Finetuning of LLMs via Alternating Optimization of LoRA
  36. NeurIPS 2025Robustifying Learning-Augmented Caching Efficiently without Compromising 1-Consistency
  37. NeurIPS 2025Robustly Learning Monotone Single-Index Models
  38. NeurIPS 2025SAD Neural Networks: Divergent Gradient Flows and Asymptotic Optimality via o-minimal Structures
  39. NeurIPS 2025Sample-Adaptivity Tradeoff in On-Demand Sampling
  40. NeurIPS 2025Scalable Neural Incentive Design with Parameterized Mean-Field Approximation
  41. NeurIPS 2025Scaling Laws for Gradient Descent and Sign Descent for Linear Bigram Models under Zipf’s Law
  42. NeurIPS 2025Second-order Optimization under Heavy-Tailed Noise: Hessian Clipping and Sample Complexity Limits
  43. NeurIPS 2025Self-Boost via Optimal Retraining: An Analysis via Approximate Message Passing
  44. NeurIPS 2025Semi-infinite Nonconvex Constrained Min-Max Optimization
  45. NeurIPS 2025Set Smoothness Unlocks Clarke Hyper-stationarity in Bilevel Optimization
  46. NeurIPS 2025Sharp Matrix Empirical Bernstein Inequalities
  47. NeurIPS 2025Sharper Convergence Rates for Nonconvex Optimisation via Reduction Mappings
  48. NeurIPS 2025Sketched Adaptive Distributed Deep Learning: A Sharp Convergence Analysis
  49. NeurIPS 2025Small Singular Values Matter: A Random Matrix Analysis of Transformer Models
  50. NeurIPS 2025Smart Surrogate Losses for Contextual Stochastic Linear Optimization with Robust Constraints

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查理论 · optimization在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "theory-optimization"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

常见问题

2023–2026 年四大会议一共有多少篇理论 · optimization论文？
共 1,871 篇，按年份分别是 2023 年 123 篇、2024 年 494 篇、2025 年 670 篇、2026 年 584 篇。
NeurIPS 2026 有多少篇理论 · optimization论文？
NeurIPS 2026 有 119 篇理论 · optimization论文，上一届是 318 篇。
ICLR 2026 有多少篇理论 · optimization论文？
ICLR 2026 有 244 篇理论 · optimization论文，上一届是 196 篇。
ICML 2026 有多少篇理论 · optimization论文？
ICML 2026 有 214 篇理论 · optimization论文，上一届是 147 篇。
CVPR 2026 有多少篇理论 · optimization论文？
CVPR 2026 有 7 篇理论 · optimization论文，上一届是 9 篇。
哪个会议的理论 · optimization论文最多？
NeurIPS，2023–2026 年共 778 篇。

「理论与统计」下的其他主题